[CUDA] Use appropriate return code for out of registers kernel launch

[GeorgeWeb]

This PR changes the returned error code for exiting the kernel launch entry point in CUDA when exceeding the maximum available registers for execution on the SM. Previously we were returning a misleading error code.

This change requires DPC++ to adapt the specific-error handling, see PR: https://github.com/intel/llvm/pull/12604.

[codecov-commenter]

Codecov Report

All modified and coverable lines are covered by tests :white_check_mark:

Comparison is base (8c604b0) 15.39% compared to head (b85dbe2) 15.39%. Report is 20 commits behind head on main.

:exclamation: Your organization needs to install the Codecov GitHub app to enable full functionality.

Additional details and impacted files

@@           Coverage Diff           @@
##             main    #1318   +/-   ##
=======================================
  Coverage   15.39%   15.39%           
=======================================
  Files         240      240           
  Lines       34099    34122   +23     
  Branches     3775     3779    +4     
=======================================
+ Hits         5250     5254    +4     
- Misses      28798    28818   +20     
+ Partials       51       50    -1     

:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.

[GeorgeWeb]

Change the returned error code for exiting the kernel launch entry point in CUDA when exceeding the maximum available registers for execution on the SM. Previously we were returning a misleading error code

Put that in your commit message, please

Good shout. Reworded now.